Moving Object Detection Software
Implementation of SOBS algorithm as described in:
L. Maddalena, A. Petrosino, A SelfOrganizing Approach to Background Subtraction for Visual Surveillance Applications, IEEE Transactions on Image Processing, DOI: 10.1109/TIP.2008.924285, Vol. 17, no. 7, pagg. 11681177, July 2008
Usage:
where
<SeqName>
: sequence name (complete path), not including frame numbers. Image sequences consist of binary PPM image frames with consecutive numbers, named in the following form
The number of digits for must be the same for all sequence frames (e.g. a sequence with 120 frames must be numbered from 1001 to 1120, and not from 1 to 120)

<#FirstFrame>, <#LastFrame>
: number of first and last sequence frame to be considered. 
[parameters]: optional, including:

n #: (square root of) number of weight vectors for each pixel. Default 3

K #: Number of initial frames for calibration. Default 200

e1 #: Distance threshold e1 for calibration phase (eqn. (2)). Default 0.1

e2 #: Distance threshold e2 for online phase (eqn. (2)). Default 0.03

c1 #: Learning rate c1 for calibration phase (eqn. (4)). Default 1.0

c2 #: Learning rate c2 for online phase (eqn. (4)). Default 0.05

g #: Value for g in eqn. (5). Default 0.7

b #: Value for b in eqn. (5). Default 1.0

tS #: Value for tS in eqn. (5). Default 0.1

tH #: Value for tH in eqn. (5). Default 10.0

s: To apply shadow removal. Default: no shadow removal

m: To save background model images. Default: do not save

l: To save just last detection mask. Default: save all

<![if !supportEmptyParas]> <![endif]>

Example of use:
where sequence WavingTrees, coming from sequences adopted in K. Toyama, J. Krumm, B. Brumitt, and B. Meyers, “Wallflower: principles and practice of background maintenance,” in Proc. 7th IEEE Conf. Computer Vision, 1999, vol. 1, pp. 255–261, has been saved in binary PPM image files named:
and stored in directory c:/Sequences/WavingTrees.
\
Download the SOBS software here. 